Embodiments are directed to a method of performing autonomous learning for updating input features used for an artificial intelligence model, the method comprising receiving updated data of an information space that includes a graph of nodes having a defined topology, the updated data including historical data of requests to the artificial intelligence model and output results associated with the requests, wherein different categories of input data corresponds to different input nodes of the graph. The method may further comprise updating edge connections between the nodes of the graph by performing path optimizations that each use a set of agents to explore the information space over cycles to reduce a cost function, each connection including a strength value, wherein during each path optimization, path information is shared between the rest of agents at each cycle for determining a next position value for each of the set of agents in the graph.
Legal claims defining the scope of protection, as filed with the USPTO.
2. The method of claim 1, wherein step c) further comprises combining two or more candidate input features into a single feature when the two or more candidate input features share a predetermined number of input nodes.
5. The method of claim 3, wherein the path information includes an error relative to a target goal.
6. The method of claim 5, further comprising performing step b) until the target goal has been met.
7. The method of claim 6, further comprising initializing the agents at a start of each cycle according to a weighted distribution that is based on a gradient of the error relative to the target goal.
9. The method of claim 7, wherein the path information includes movement vectors that point in a direction of new information.
10. The method of claim 7, wherein the set of agents are initialized at the start of each cycle based on specified search criteria, and wherein the specified search criteria include a definition of the target goal, a definition of the cost function, a predetermined cost requirement, and an initial distribution of agents.
11. The method of claim 1, wherein the graph is sharded into overlapping subgraphs that are searched for a solution by the agents in parallel.
12. The method of claim 11, further comprising distributing the subgraphs amongst cores in a multi-core graphic processing unit.
14. The server computer of claim 13, wherein step c) further comprises combining, by the server computer, two or more candidate input features into a single feature when the two or more candidate input features share a predetermined number of input nodes.
17. The server computer of claim 15, wherein the path information includes a gradient of an error relative to a target goal.
18. The server computer of claim 17, wherein the method further comprises performing step b) until the target goal has been met.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
May 9, 2017
February 21, 2023
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.